Skip to content
mcp/harbor
LangChain

AI Guard for LangChain

io.github.ai-guard-dev/ai-guard

Guardrails for AI-written JS/TS: scans, weakened-test checks, package checks, verify before done.

client:LangChain transport:stdio runtime:npm

Install AI Guard in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "ai-guard": {
            "transport": "stdio",
            "command": "npx",
            "args": ["-y", "eslint-plugin-ai-guard"],
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

AI Guard in other clients

AI Guard MCP server